Muscular motion estimation from 4-D ultrasound image using Kalman filter and rotation-invariant feature descriptor

Chi Hung Tsai, Hsin Chen Chen, Yung-Nien Sun, Fong-chin Su, Li-Chieh Kuo

研究成果: Conference contribution

摘要

Muscular motion estimation in ultrasound images is of great importance for investigating causes of musculoskeletal conditions in pathological examinations. However, the quality of ultrasound images is usually depressed due to speckle noises and temporal decorrelation of speckle patterns, making certain difficulties in motion estimation. To resolve the problem, this paper presents a new model-based tracking method for estimating the perimysium motion from 4-D ultrasound images. From the first frame of the given motion images, the proposed method builds a perimysium model, which consists of 3-D surface and rotation-invariant feature descriptor (RIFD) to characterize its structural and image appearances. Then, the model is applied to the next frame using Kalman filter for estimating the best matching position with the highest similarity of RIFD. The estimation is used to update the motion state for predicting and refining the model position in the next frame. The Kalman filtering is iteratively performed until the entire image sequence is processed. Overall, the proposed method efficiently combines the structure, image and motion priors, so it can overcome the aforementioned difficulties. Experimental results showed that the proposed method can provide reliable and accurate estimation of perimysium motion with tracking errors 6.26 voxels using three 4-D ultrasound volumes.

原文English
主出版物標題2013 3rd International Conference on Innovative Computing Technology, INTECH 2013
頁面29-34
頁數6
DOIs
出版狀態Published - 2013
事件2013 3rd International Conference on Innovative Computing Technology, INTECH 2013 - London, United Kingdom
持續時間: 2013 八月 292013 八月 31

Other

Other2013 3rd International Conference on Innovative Computing Technology, INTECH 2013
國家United Kingdom
城市London
期間13-08-2913-08-31

指紋

Motion estimation
Kalman filters
Ultrasonics
Speckle
Acoustic noise
Refining
Kalman filter
Ultrasound

All Science Journal Classification (ASJC) codes

  • Management of Technology and Innovation

引用此文

Tsai, C. H., Chen, H. C., Sun, Y-N., Su, F., & Kuo, L-C. (2013). Muscular motion estimation from 4-D ultrasound image using Kalman filter and rotation-invariant feature descriptor. 於 2013 3rd International Conference on Innovative Computing Technology, INTECH 2013 (頁 29-34). [6653723] https://doi.org/10.1109/INTECH.2013.6653723
Tsai, Chi Hung ; Chen, Hsin Chen ; Sun, Yung-Nien ; Su, Fong-chin ; Kuo, Li-Chieh. / Muscular motion estimation from 4-D ultrasound image using Kalman filter and rotation-invariant feature descriptor. 2013 3rd International Conference on Innovative Computing Technology, INTECH 2013. 2013. 頁 29-34
@inproceedings{9e29c570ac114147a9c735ac6d77fadf,
title = "Muscular motion estimation from 4-D ultrasound image using Kalman filter and rotation-invariant feature descriptor",
abstract = "Muscular motion estimation in ultrasound images is of great importance for investigating causes of musculoskeletal conditions in pathological examinations. However, the quality of ultrasound images is usually depressed due to speckle noises and temporal decorrelation of speckle patterns, making certain difficulties in motion estimation. To resolve the problem, this paper presents a new model-based tracking method for estimating the perimysium motion from 4-D ultrasound images. From the first frame of the given motion images, the proposed method builds a perimysium model, which consists of 3-D surface and rotation-invariant feature descriptor (RIFD) to characterize its structural and image appearances. Then, the model is applied to the next frame using Kalman filter for estimating the best matching position with the highest similarity of RIFD. The estimation is used to update the motion state for predicting and refining the model position in the next frame. The Kalman filtering is iteratively performed until the entire image sequence is processed. Overall, the proposed method efficiently combines the structure, image and motion priors, so it can overcome the aforementioned difficulties. Experimental results showed that the proposed method can provide reliable and accurate estimation of perimysium motion with tracking errors 6.26 voxels using three 4-D ultrasound volumes.",
author = "Tsai, {Chi Hung} and Chen, {Hsin Chen} and Yung-Nien Sun and Fong-chin Su and Li-Chieh Kuo",
year = "2013",
doi = "10.1109/INTECH.2013.6653723",
language = "English",
isbn = "9781479900473",
pages = "29--34",
booktitle = "2013 3rd International Conference on Innovative Computing Technology, INTECH 2013",

}

Tsai, CH, Chen, HC, Sun, Y-N, Su, F & Kuo, L-C 2013, Muscular motion estimation from 4-D ultrasound image using Kalman filter and rotation-invariant feature descriptor. 於 2013 3rd International Conference on Innovative Computing Technology, INTECH 2013., 6653723, 頁 29-34, 2013 3rd International Conference on Innovative Computing Technology, INTECH 2013, London, United Kingdom, 13-08-29. https://doi.org/10.1109/INTECH.2013.6653723

Muscular motion estimation from 4-D ultrasound image using Kalman filter and rotation-invariant feature descriptor. / Tsai, Chi Hung; Chen, Hsin Chen; Sun, Yung-Nien; Su, Fong-chin; Kuo, Li-Chieh.

2013 3rd International Conference on Innovative Computing Technology, INTECH 2013. 2013. p. 29-34 6653723.

研究成果: Conference contribution

TY - GEN

T1 - Muscular motion estimation from 4-D ultrasound image using Kalman filter and rotation-invariant feature descriptor

AU - Tsai, Chi Hung

AU - Chen, Hsin Chen

AU - Sun, Yung-Nien

AU - Su, Fong-chin

AU - Kuo, Li-Chieh

PY - 2013

Y1 - 2013

N2 - Muscular motion estimation in ultrasound images is of great importance for investigating causes of musculoskeletal conditions in pathological examinations. However, the quality of ultrasound images is usually depressed due to speckle noises and temporal decorrelation of speckle patterns, making certain difficulties in motion estimation. To resolve the problem, this paper presents a new model-based tracking method for estimating the perimysium motion from 4-D ultrasound images. From the first frame of the given motion images, the proposed method builds a perimysium model, which consists of 3-D surface and rotation-invariant feature descriptor (RIFD) to characterize its structural and image appearances. Then, the model is applied to the next frame using Kalman filter for estimating the best matching position with the highest similarity of RIFD. The estimation is used to update the motion state for predicting and refining the model position in the next frame. The Kalman filtering is iteratively performed until the entire image sequence is processed. Overall, the proposed method efficiently combines the structure, image and motion priors, so it can overcome the aforementioned difficulties. Experimental results showed that the proposed method can provide reliable and accurate estimation of perimysium motion with tracking errors 6.26 voxels using three 4-D ultrasound volumes.

AB - Muscular motion estimation in ultrasound images is of great importance for investigating causes of musculoskeletal conditions in pathological examinations. However, the quality of ultrasound images is usually depressed due to speckle noises and temporal decorrelation of speckle patterns, making certain difficulties in motion estimation. To resolve the problem, this paper presents a new model-based tracking method for estimating the perimysium motion from 4-D ultrasound images. From the first frame of the given motion images, the proposed method builds a perimysium model, which consists of 3-D surface and rotation-invariant feature descriptor (RIFD) to characterize its structural and image appearances. Then, the model is applied to the next frame using Kalman filter for estimating the best matching position with the highest similarity of RIFD. The estimation is used to update the motion state for predicting and refining the model position in the next frame. The Kalman filtering is iteratively performed until the entire image sequence is processed. Overall, the proposed method efficiently combines the structure, image and motion priors, so it can overcome the aforementioned difficulties. Experimental results showed that the proposed method can provide reliable and accurate estimation of perimysium motion with tracking errors 6.26 voxels using three 4-D ultrasound volumes.

UR - http://www.scopus.com/inward/record.url?scp=84891066788&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891066788&partnerID=8YFLogxK

U2 - 10.1109/INTECH.2013.6653723

DO - 10.1109/INTECH.2013.6653723

M3 - Conference contribution

SN - 9781479900473

SP - 29

EP - 34

BT - 2013 3rd International Conference on Innovative Computing Technology, INTECH 2013

ER -

Tsai CH, Chen HC, Sun Y-N, Su F, Kuo L-C. Muscular motion estimation from 4-D ultrasound image using Kalman filter and rotation-invariant feature descriptor. 於 2013 3rd International Conference on Innovative Computing Technology, INTECH 2013. 2013. p. 29-34. 6653723 https://doi.org/10.1109/INTECH.2013.6653723